1. Joint Modeling
1.1 Trace plots for convergence check
The current MCMC setting is:
- 100,000 iteration;
- 90,000 burn-in;
- 10 thinning.
1.2 Gelman and Rubin’s convergence check
## Potential scale reduction factors:
##
## Point est. Upper C.I.
## HDevsum 1.01 1.02
## LDevsum 1.11 1.30
## dh0 1.83 2.90
## dh1 1.05 1.13
## dh2 2.48 4.10
## dh3 1.14 1.38
## dl0 2.06 3.34
## dl1 1.04 1.09
## dl2 2.43 4.05
## dl3 1.18 1.46
##
## Multivariate psrf
##
## 2.24
1.3 ACF Plots
Here we plotted ACF plots for the following variables:
- Total deviance;
- Variables that didn’t pass the convergence check.
1.4 WAIC results
| LevelH | LevelL | |
|---|---|---|
| DIC | 1159.08471 | 22009.0560 |
| DIC3 | 1122.73327 | 22065.5332 |
| PWAIC | 26.60746 | 190.6823 |
| WAIC | 1136.48862 | 22078.4937 |
2. Separate Modeling
2.1 Trace plots for convergence check
The current MCMC setting is:
- 100,000 iteration;
- 90,000 burn-in;
- 10 thinning.
2.2 Gelman and Rubin’s convergence check
## Potential scale reduction factors:
##
## Point est. Upper C.I.
## HDevsum 1.02 1.06
## LDevsum 1.00 1.00
## dh0 3.67 6.86
## dh1 26.47 50.69
## dh2 17.64 35.63
## dh3 7.41 13.34
## dl0 1.49 2.31
## dl1 1.07 1.19
## dl2 1.06 1.15
## dl3 1.06 1.16
##
## Multivariate psrf
##
## 23.7
2.3 ACF Plots
Here we plotted ACF plots for the following variables:
- Total deviance;
- Variables that didn’t pass the convergence check.
2.4 WAIC results
| LevelH | LevelL | |
|---|---|---|
| DIC | 1380.93948 | 27389.409 |
| DIC3 | 1247.25373 | 27460.944 |
| PWAIC | 91.08029 | 121.096 |
| WAIC | 1316.55449 | 27464.858 |